Nemotron Nano 3 30B-A3BQ4_K_M
requires 32 GB+ memory · 1.0M context · Workstation
20 GBWeights
← All models4K 25 GB 8K 26 GB 16K 28 GB 33K 30 GB 66K 31 GB 131K 33 GB 1.0M 38 GB
Nemotron Nano 3
NVIDIA hybrid MoE for agents: reasoning, coding, and tools with 1M-token context and high throughput. The 30B-A3B active path stays efficient while the long window holds entire projects.
- Maker
- NVIDIA
- Architecture
- Hybrid MoE · 1M context
- Fits from
- Workstation · 32 GB+ RAM
- Context
- up to 1.0M
- Runs
- Local Intelligence
AgentsReasoningCodingLong-horizon agentsCoding1M context
Sizes
Memory at context length
Approximate working set for Nemotron Nano 3 30B-A3B as context grows.
